Rishi Jha is a PhD student researcher at Cornell Tech with nine years of industry and research experience at the intersection of machine learning, security, and agentic systems. He studies how generative models encode knowledge and leverages that insight to design safer multi-agent and alignment defenses, with recent work on the universal geometry of embeddings and agentic security. Rishi has shipped and productionized defenses at Microsoft (including a patent-pending spectral detection approach and a proposed core safety layer for multi-agent deployments) and is currently investigating agentic security at Google. His research background spans high-impact backdoor and robustness work—e.g., FLIP, a trajectory-matching label-poisoning attack that achieves near-perfect success with minimal data poisoning—alongside applied systems engineering from startups to enterprise products. Collected training in CS and math (UW MS and BS, now Cornell PhD) complements his ability to move ideas from theory to deployed safeguards. An uncommon throughline in his work is pairing principled theoretical insight about representations with pragmatic, testable defenses that teams adopt.
8 years of coding experience
4 years of employment as a software developer
Master of Science - MS Computer Science, Master of Science - MS Computer Science at University of Washington
The Overlake School
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Cornell University
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.